Affine Invariant Interacting Langevin Dynamics for Bayesian Inference

DOI10.1137/19M1304891zbMath1472.65118arXiv1912.02859MaRDI QIDQ4964234

Nikolas Nüsken, Sebastian Reich, Alfredo Garbuno-Inigo

Publication date: 25 February 2021

Published in: SIAM Journal on Applied Dynamical Systems (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1912.02859

zbMATH Keywords

gradient flowLangevin dynamicsBayesian inferenceinteracting particle systemsmultiplicative noiseaffine invariancegradient-free

Mathematics Subject Classification ID

Bayesian inference (62F15) Derivative-free methods and methods using generalized derivatives (90C56) Flows in porous media; filtration; seepage (76S05) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31) Numerical solutions to stochastic differential and integral equations (65C30) Gradient-like behavior; isolated (locally maximal) invariant sets; attractors, repellers for topological dynamical systems (37B35) Numerical methods for inverse problems for initial value and initial-boundary value problems involving PDEs (65M32) Probabilistic methods, particle methods, etc. for initial value and initial-boundary value problems involving PDEs (65M75)

Related Items (21)

Derivative-Free Bayesian Inversion Using Multiscale Dynamics ⋮ Continuous Time Limit of the Stochastic Ensemble Kalman Inversion: Strong Convergence Analysis ⋮ GP-ETAS: semiparametric Bayesian inference for the spatio-temporal epidemic type aftershock sequence model ⋮ Efficient derivative-free Bayesian inference for large-scale inverse problems ⋮ Constrained ensemble Langevin Monte Carlo ⋮ Ensemble Inference Methods for Models With Noisy and Expensive Likelihoods ⋮ Iterated Kalman methodology for inverse problems ⋮ Ensemble Markov Chain Monte Carlo with Teleporting Walkers ⋮ A Benchmark for the Bayesian Inversion of Coefficients in Partial Differential Equations ⋮ Consensus‐based sampling ⋮ Scaling Up Bayesian Uncertainty Quantification for Inverse Problems Using Deep Neural Networks ⋮ Complete Deterministic Dynamics and Spectral Decomposition of the Linear Ensemble Kalman Inversion ⋮ Bayesian spatiotemporal modeling for inverse problems ⋮ Ensemble-Based Gradient Inference for Particle Methods in Optimization and Sampling ⋮ Stein variational gradient descent: many-particle and long-time asymptotics ⋮ Affine-invariant ensemble transform methods for logistic regression ⋮ Response theory and phase transitions for the thermodynamic limit of interacting identical systems ⋮ Ensemble slice sampling. Parallel, black-box and gradient-free inference for correlated \& multimodal distributions ⋮ Ensemble Kalman inversion for nonlinear problems: weights, consistency, and variance bounds ⋮ Fokker--Planck Particle Systems for Bayesian Inference: Computational Approaches ⋮ Gradient flow structure and convergence analysis of the ensemble Kalman inversion for nonlinear forward models

Uses Software

• EnKF
• EnsembleQN

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Ensemble samplers with affine invariance
• Information-geometric Markov chain Monte Carlo methods using diffusions
• A dynamical systems framework for intermittent data assimilation
• Recurrence and invariant measures for degenerate diffusions
• Stochastic stability of differential equations. With contributions by G. N. Milstein and M. B. Nevelson
• Langevin diffusions and Metropolis-Hastings algorithms
• Ensemble preconditioning for Markov chain Monte Carlo simulation
• Using perturbed underdamped Langevin dynamics to efficiently sample from probability distributions
• A computational fluid mechanics solution to the Monge-Kantorovich mass transfer problem
• Discrete gradients for computational Bayesian inference
• Stability of Markovian processes II: continuous-time processes and sampled chains
• Stability of Markovian processes III: Foster–Lyapunov criteria for continuous-time processes
• The Variational Formulation of the Fokker--Planck Equation
• Riemann Manifold Langevin and Hamiltonian Monte Carlo Methods
• Interacting Langevin Diffusions: Gradient Structure and Ensemble Kalman Sampler
• Stochastic Processes and Applications
• Probabilistic Forecasting and Bayesian Data Assimilation
• Nonlinear diffusion equations with variable coefficients as gradient flows in Wasserstein spaces
• Ensemble Kalman inversion: a derivative-free technique for machine learning tasks
• Data Assimilation
• Analysis of the Ensemble Kalman Filter for Inverse Problems
• Ensemble filter techniques for intermittent data assimilation - a survey
• Fluctuations and Irreversible Process. II. Systems with Kinetic Energy
• Data Assimilation
• Optimal Transport

This page was built for publication: Affine Invariant Interacting Langevin Dynamics for Bayesian Inference